English

RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies

Robotics 2026-05-15 v3 Artificial Intelligence

Abstract

The pursuit of general-purpose robotics has yielded impressive foundation models, yet simulation-based benchmarking remains a bottleneck due to rapid performance saturation and a lack of true generalization testing. Existing benchmarks often exhibit significant domain overlap between training and evaluation, trivializing success rates and obscuring insights into robustness. We introduce RoboLab, a simulation benchmarking framework designed to address these challenges. Concretely, our framework is designed to answer two questions: (1) to what extent can we understand the performance of a real-world policy by analyzing its behavior in simulation, and (2) which factor most strongly affect policy behavior. First, RoboLab enables human-authored and LLM-enabled generation of scenes and tasks in a robot- and policy-agnostic manner within a high-fidelity simulation environment. We introduce an accompanying RoboLab-120 benchmark, consisting of 120 tasks categorized into three competency axes: visual, procedural, relational, across three difficulty levels. Second, we introduce a systematic analysis of real-world policies that quantify both their performance and the sensitivity of their behavior to controlled perturbations, exposing significant performance gap in current state-of-the-art models. By providing granular metrics and a scalable toolset, RoboLab offers a scalable framework for evaluating the true generalization capabilities of task-generalist robotic policies. Project website: https://research.nvidia.com/labs/srl/projects/robolab/.

Keywords

Cite

@article{arxiv.2604.09860,
  title  = {RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies},
  author = {Xuning Yang and Rishit Dagli and Alex Zook and Hugo Hadfield and Ankit Goyal and Stan Birchfield and Fabio Ramos and Jonathan Tremblay},
  journal= {arXiv preprint arXiv:2604.09860},
  year   = {2026}
}